{"url":"/task/entity-resolution","name":"Entity Resolution","slug":"entity-resolution","description_markdown":"**Entity resolution** (also known as entity matching, record linkage, or duplicate detection) is the task of finding records that refer to the same real-world entity across different data sources (e.g., data files, books, websites, and databases). (Source: Wikipedia)\r\n\r\nSurveys on entity resolution:\r\n\r\n- [Christophides et al.: End-to-End Entity Resolution for Big Data: A Survey](https://arxiv.org/pdf/1905.06397.pdf), 2020.\r\n\r\n- [Barlaug and Gulla: Neural Networks for Entity Matching: A Survey](https://arxiv.org/pdf/2010.11075.pdf), 2021.\r\n\r\nThe task of entity resolution is closely related to the task of [entity alignment](https://paperswithcode.com/task/entity-alignment) which focuses on matching entities between knowledge bases. The task of [entity linking](https://paperswithcode.com/task/entity-linking) differs from entity resolution as entity linking focuses on identifying entity mentions in free text.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":184,"papers_with_code":55,"benchmarks":11,"benchmark_tables_in_archive":11,"benchmark_tables_shown":11,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":12,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/entity-resolution-on-amazon-google","slug":"entity-resolution-on-amazon-google","dataset":"Amazon-Google","dataset_url":"/dataset/amazon-google","rows_in_archive":17,"metrics":["F1 (%)"],"first_row_in_archive_order":{"model":"gpt4-0613_fewshot-10","paper_title":"Entity Matching using Large Language Models","paper_url":"/paper/entity-matching-using-large-language-models","paper_date":"2023-10-17","arxiv_id":"2310.11244","code_links":[{"title":"wbsg-uni-mannheim/matchgpt","url":"https://github.com/wbsg-uni-mannheim/matchgpt"}],"syntology":null}},{"leaderboard":"/sota/entity-resolution-on-abt-buy","slug":"entity-resolution-on-abt-buy","dataset":"Abt-Buy","dataset_url":"/dataset/abt-buy","rows_in_archive":16,"metrics":["F1 (%)"],"first_row_in_archive_order":{"model":"gpt4-0613_zeroshot","paper_title":"Entity Matching using Large Language Models","paper_url":"/paper/entity-matching-using-large-language-models","paper_date":"2023-10-17","arxiv_id":"2310.11244","code_links":[{"title":"wbsg-uni-mannheim/matchgpt","url":"https://github.com/wbsg-uni-mannheim/matchgpt"}],"syntology":null}},{"leaderboard":"/sota/entity-resolution-on-wdc-products-80-cc-seen","slug":"entity-resolution-on-wdc-products-80-cc-seen","dataset":"WDC Products-80%cc-seen-medium","dataset_url":"/dataset/wdc-products-1","rows_in_archive":13,"metrics":["F1 (%)"],"first_row_in_archive_order":{"model":"gpt4-0613_zeroshot","paper_title":"Entity Matching using Large Language Models","paper_url":"/paper/entity-matching-using-large-language-models","paper_date":"2023-10-17","arxiv_id":"2310.11244","code_links":[{"title":"wbsg-uni-mannheim/matchgpt","url":"https://github.com/wbsg-uni-mannheim/matchgpt"}],"syntology":null}},{"leaderboard":"/sota/entity-resolution-on-wdc-computers-small","slug":"entity-resolution-on-wdc-computers-small","dataset":"WDC Computers-small","dataset_url":"/dataset/wdc-products","rows_in_archive":6,"metrics":["F1 (%)"],"first_row_in_archive_order":{"model":"BERT","paper_title":"Intermediate Training of BERT for Product Matching","paper_url":"/paper/intermediate-training-of-bert-for-product","paper_date":"2020-08-31","arxiv_id":null,"code_links":[{"title":"weyoun2211/productbert-intermediate","url":"https://github.com/weyoun2211/productbert-intermediate"},{"title":"wbsg-uni-mannheim/productbert-intermediate","url":"https://github.com/wbsg-uni-mannheim/productbert-intermediate"}],"syntology":null}},{"leaderboard":"/sota/entity-resolution-on-wdc-computers-xlarge","slug":"entity-resolution-on-wdc-computers-xlarge","dataset":"WDC Computers-xlarge","dataset_url":"/dataset/wdc-products","rows_in_archive":6,"metrics":["F1 (%)"],"first_row_in_archive_order":{"model":"RoBERTa-SupCon","paper_title":"Supervised Contrastive Learning for Product Matching","paper_url":"/paper/supervised-contrastive-learning-for-product","paper_date":"2022-02-04","arxiv_id":"2202.02098","code_links":[{"title":"wbsg-uni-mannheim/contrastive-product-matching","url":"https://github.com/wbsg-uni-mannheim/contrastive-product-matching"}],"syntology":null}},{"leaderboard":"/sota/entity-resolution-on-wdc-products-50-cc","slug":"entity-resolution-on-wdc-products-50-cc","dataset":"WDC Products-50%cc-unseen-medium","dataset_url":"/dataset/wdc-products-1","rows_in_archive":4,"metrics":["F1 (%)"],"first_row_in_archive_order":{"model":"RoBERTa-base","paper_title":"WDC Products: A Multi-Dimensional Entity Matching Benchmark","paper_url":"/paper/wdc-products-a-multi-dimensional-entity","paper_date":"2023-01-23","arxiv_id":"2301.09521","code_links":[{"title":"wbsg-uni-mannheim/wdcproducts","url":"https://github.com/wbsg-uni-mannheim/wdcproducts"}],"syntology":null}},{"leaderboard":"/sota/entity-resolution-on-wdc-watches-small","slug":"entity-resolution-on-wdc-watches-small","dataset":"WDC Watches-small","dataset_url":"/dataset/wdc-products","rows_in_archive":4,"metrics":["F1 (%)"],"first_row_in_archive_order":{"model":"HG","paper_title":"Entity Resolution with Hierarchical Graph Attention Networks","paper_url":"/paper/entity-resolution-with-hierarchical-graph","paper_date":"2022-06-01","arxiv_id":null,"code_links":[{"title":"CGCL-codes/HierGAT","url":"https://github.com/CGCL-codes/HierGAT"}],"syntology":null}},{"leaderboard":"/sota/entity-resolution-on-musicbrainz20k","slug":"entity-resolution-on-musicbrainz20k","dataset":"MusicBrainz20K","dataset_url":"/dataset/musicbrainz20k","rows_in_archive":3,"metrics":["F1"],"first_row_in_archive_order":{"model":"ALMSER-GB","paper_title":"Graph-boosted Active Learning for Multi-Source Entity Resolution","paper_url":"/paper/graph-boosted-active-learning-for-multi","paper_date":"2021-09-30","arxiv_id":null,"code_links":[{"title":"wbsg-uni-mannheim/ALMSER-GB","url":"https://github.com/wbsg-uni-mannheim/ALMSER-GB"}],"syntology":null}},{"leaderboard":"/sota/entity-resolution-on-wdc-watches-xlarge","slug":"entity-resolution-on-wdc-watches-xlarge","dataset":"WDC Watches-xlarge","dataset_url":"/dataset/wdc-products","rows_in_archive":3,"metrics":["F1 (%)"],"first_row_in_archive_order":{"model":"JointBERT","paper_title":"Dual-Objective Fine-Tuning of BERT for Entity Matching","paper_url":"/paper/dual-objective-fine-tuning-of-bert-for-entity","paper_date":"2021-06-01","arxiv_id":null,"code_links":[{"title":"wbsg-uni-mannheim/jointbert","url":"https://github.com/wbsg-uni-mannheim/jointbert"}],"syntology":null}},{"leaderboard":"/sota/entity-resolution-on-wdc-products-80-cc-seen-1","slug":"entity-resolution-on-wdc-products-80-cc-seen-1","dataset":"WDC Products-80%cc-seen-medium-multi","dataset_url":"/dataset/wdc-products-1","rows_in_archive":2,"metrics":["F1 Micro"],"first_row_in_archive_order":{"model":"RoBERTa-SupCon","paper_title":"WDC Products: A Multi-Dimensional Entity Matching Benchmark","paper_url":"/paper/wdc-products-a-multi-dimensional-entity","paper_date":"2023-01-23","arxiv_id":"2301.09521","code_links":[{"title":"wbsg-uni-mannheim/wdcproducts","url":"https://github.com/wbsg-uni-mannheim/wdcproducts"}],"syntology":null}},{"leaderboard":"/sota/entity-resolution-on-wdc-products","slug":"entity-resolution-on-wdc-products","dataset":"WDC Products","dataset_url":"/dataset/wdc-products-1","rows_in_archive":1,"metrics":["F1 (%)"],"first_row_in_archive_order":{"model":"gpt-4o-2024-08-06_fine_tuned_wdc_small","paper_title":"Fine-tuning Large Language Models for Entity Matching","paper_url":"/paper/fine-tuning-large-language-models-for-entity","paper_date":"2024-09-12","arxiv_id":"2409.08185","code_links":[{"title":"wbsg-uni-mannheim/tailormatch","url":"https://github.com/wbsg-uni-mannheim/tailormatch"}],"syntology":null}}],"datasets":[{"url":"/dataset/amazon-google","name":"Amazon-Google","full_name":"","num_papers_in_archive":20},{"url":"/dataset/abt-buy","name":"Abt-Buy","full_name":"","num_papers_in_archive":19},{"url":"/dataset/wdc-products","name":"WDC LSPM","full_name":"","num_papers_in_archive":8},{"url":"/dataset/dblp-temporal","name":"DBLP Temporal","full_name":"","num_papers_in_archive":7},{"url":"/dataset/wdc-products-1","name":"WDC Products","full_name":"","num_papers_in_archive":6},{"url":"/dataset/musicbrainz20k","name":"MusicBrainz20K","full_name":"","num_papers_in_archive":2},{"url":"/dataset/binette-s-2022-inventors-benchmark","name":"Binette's 2022 Inventors Benchmark","full_name":"Binette's 2022 Inventors Benchmark","num_papers_in_archive":1},{"url":"/dataset/cerec","name":"CEREC","full_name":"Corpus for Entity Resolution in Email Conversations","num_papers_in_archive":1},{"url":"/dataset/diaforge-utc-r-0725","name":"diaforge-utc-r-0725","full_name":"DiaFORGE UTC: Unified Tool-Calling Conversations Dataset","num_papers_in_archive":1},{"url":"/dataset/moviegraphbenchmark","name":"MovieGraphBenchmark","full_name":"","num_papers_in_archive":1},{"url":"/dataset/pizza","name":"PIZZA","full_name":"","num_papers_in_archive":1},{"url":"/dataset/weibo-douban","name":"Weibo-Douban","full_name":"WD","num_papers_in_archive":1}],"subtasks":[{"url":"/task/blocking","name":"Blocking"}],"parent_tasks":[{"url":"/task/data-integration","name":"Data Integration"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":55,"tagged_in_all":184,"items":[{"url":"/paper/d-blink-distributed-end-to-end-bayesian","title":"d-blink: Distributed End-to-End Bayesian Entity Resolution","date":"2019-09-13","arxiv_id":"1909.06039","repositories_listed":4,"syntology":null},{"url":"/paper/estimating-the-performance-of-entity","title":"Estimating the Performance of Entity Resolution Algorithms: Lessons Learned Through PatentsView.org","date":"2022-10-03","arxiv_id":"2210.01230","repositories_listed":3,"syntology":null},{"url":"/paper/match-compare-or-select-an-investigation-of","title":"Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching","date":"2024-05-27","arxiv_id":"2405.16884","repositories_listed":2,"syntology":null},{"url":"/paper/towards-universal-dense-blocking-for-entity","title":"Towards Universal Dense Blocking for Entity Resolution","date":"2024-04-23","arxiv_id":"2404.14831","repositories_listed":2,"syntology":null},{"url":"/paper/pizza-a-new-benchmark-for-complex-end-to-end","title":"PIZZA: A new benchmark for complex end-to-end task-oriented parsing","date":"2022-12-01","arxiv_id":"2212.00265","repositories_listed":2,"syntology":null},{"url":"/paper/can-foundation-models-wrangle-your-data","title":"Can Foundation Models Wrangle Your Data?","date":"2022-05-20","arxiv_id":"2205.09911","repositories_listed":2,"syntology":null},{"url":"/paper/a-deep-learning-approach-to-geographical","title":"A Deep Learning Approach to Geographical Candidate Selection through Toponym Matching","date":"2020-09-17","arxiv_id":"2009.08114","repositories_listed":2,"syntology":null},{"url":"/paper/intermediate-training-of-bert-for-product","title":"Intermediate Training of BERT for Product Matching","date":"2020-08-31","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/chatpd-an-llm-driven-paper-dataset-networking","title":"ChatPD: An LLM-driven Paper-Dataset Networking System","date":"2025-05-28","arxiv_id":"2505.22349","repositories_listed":1,"syntology":null},{"url":"/paper/text2tracks-prompt-based-music-recommendation","title":"Text2Tracks: Prompt-based Music Recommendation via Generative Retrieval","date":"2025-03-31","arxiv_id":"2503.24193","repositories_listed":1,"syntology":null},{"url":"/paper/bonafide-at-legallens-2024-shared-task-using","title":"Bonafide at LegalLens 2024 Shared Task: Using Lightweight DeBERTa Based Encoder For Legal Violation Detection and Resolution","date":"2024-10-30","arxiv_id":"2410.22977","repositories_listed":1,"syntology":null},{"url":"/paper/t-kaer-transparency-enhanced-knowledge","title":"T-KAER: Transparency-enhanced Knowledge-Augmented Entity Resolution Framework","date":"2024-09-30","arxiv_id":"2410.00218","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-large-language-models-for-entity","title":"Fine-tuning Large Language Models for Entity Matching","date":"2024-09-12","arxiv_id":"2409.08185","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-evaluate-entity-resolution-systems-an","title":"How to Evaluate Entity Resolution Systems: An Entity-Centric Framework with Application to Inventor Name Disambiguation","date":"2024-04-08","arxiv_id":"2404.05622","repositories_listed":1,"syntology":null},{"url":"/paper/cost-effective-in-context-learning-for-entity","title":"Cost-Effective In-Context Learning for Entity Resolution: A Design Space Exploration","date":"2023-12-07","arxiv_id":"2312.03987","repositories_listed":1,"syntology":null},{"url":"/paper/entity-matching-using-large-language-models","title":"Entity Matching using Large Language Models","date":"2023-10-17","arxiv_id":"2310.11244","repositories_listed":1,"syntology":null},{"url":"/paper/a-critical-re-evaluation-of-benchmark","title":"A Critical Re-evaluation of Benchmark Datasets for (Deep) Learning-Based Matching Algorithms","date":"2023-07-03","arxiv_id":"2307.01231","repositories_listed":1,"syntology":null},{"url":"/paper/using-chatgpt-for-entity-matching","title":"Using ChatGPT for Entity Matching","date":"2023-05-05","arxiv_id":"2305.03423","repositories_listed":1,"syntology":null},{"url":"/paper/unicorn-a-unified-multi-tasking-model-for","title":"Unicorn: A Unified Multi-tasking Model for Supporting Matching Tasks in Data Integration","date":"2023-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pre-trained-embeddings-for-entity-resolution","title":"Pre-trained Embeddings for Entity Resolution: An Experimental Analysis [Experiment, Analysis & Benchmark]","date":"2023-04-24","arxiv_id":"2304.12329","repositories_listed":1,"syntology":null},{"url":"/paper/sc-block-supervised-contrastive-blocking","title":"SC-Block: Supervised Contrastive Blocking within Entity Resolution Pipelines","date":"2023-03-06","arxiv_id":"2303.03132","repositories_listed":1,"syntology":null},{"url":"/paper/wdc-products-a-multi-dimensional-entity","title":"WDC Products: A Multi-Dimensional Entity Matching Benchmark","date":"2023-01-23","arxiv_id":"2301.09521","repositories_listed":1,"syntology":null},{"url":"/paper/deduplication-over-heterogeneous-attribute","title":"Deduplication Over Heterogeneous Attribute Types (D-HAT)","date":"2022-11-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/probing-the-robustness-of-pre-trained","title":"Probing the Robustness of Pre-trained Language Models for Entity Matching","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/flexer-flexible-entity-resolution-for","title":"FlexER: Flexible Entity Resolution for Multiple Intents","date":"2022-08-23","arxiv_id":"2209.07569","repositories_listed":1,"syntology":null},{"url":"/paper/entity-resolution-with-hierarchical-graph","title":"Entity Resolution with Hierarchical Graph Attention Networks","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/domain-adaptation-for-deep-entity-resolution","title":"Domain Adaptation for Deep Entity Resolution: A Design Space Exploration","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/banglabiomed-a-biomedical-named-entity","title":"BanglaBioMed: A Biomedical Named-Entity Annotated Corpus for Bangla (Bengali)","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-critical-re-evaluation-of-neural-methods","title":"A Critical Re-evaluation of Neural Methods for Entity Alignment","date":"2022-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-how-bert-performs-entity-matching","title":"Analyzing how BERT performs entity matching","date":"2022-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":2,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}